rephrase export steps

app.py

@@ -78,21 +78,24 @@ TITLE = """
     "
 >
 <h1 style="font-weight: 900; margin-bottom: 10px; margin-top: 10px;">
-    Export your Transformers and Diffusers model to OpenVINO with 🤗 Optimum Intel (experimental)
+    Export your model to OpenVINO with Optimum Intel
 </h1>
 </div>
 """
 
 DESCRIPTION = """
-This Space allows you to automatically export to the OpenVINO format various 🤗 Transformers and Diffusers PyTorch models hosted on the Hugging Face Hub.
+This Space allows you to automatically export your model to the OpenVINO format.
 
-Once exported, you will be able to load the resulting model using the [🤗 Optimum Intel](https://huggingface.co/docs/optimum/intel/inference).
+To export your model you need:
+- A read-access token from [https://huggingface.co/settings/tokens](https://huggingface.co/settings/tokens).
+ Read access is enough given that we will open a PR against the source repo.
+- A model id of the model you'd like to export (for example: [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english))
+- A [task](https://huggingface.co/docs/optimum/main/en/exporters/task_manager#pytorch) that will be used to load the model before exporting it. If set to "auto", the task will be automatically inferred. 
 
-To export your model, the steps are as following:
-- Paste a read-access token from [https://huggingface.co/settings/tokens](https://huggingface.co/settings/tokens). Read access is enough given that we will open a PR against the source repo.
-- Input a model id from the Hub (for example: [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english))
-- Click "Export"
-- That’s it! You’ll get feedback if it works or not, and if it worked, you’ll get the URL of the opened PR 🔥
+That's it ! 🔥
+
+After the model conversion, we will open a PR against the source repo.
+You will then be able to load the resulting model and run inference using [Optimum Intel](https://huggingface.co/docs/optimum/intel/inference).
 """
 
 with gr.Blocks() as demo: